#claude code

A verified $214 bill for a production rewrite, checked against the source transcript, sits beside a corpus of about 2,900 tech talks on coding-agent costs.

Twenty days of my own Claude Code and Codex usage, measured three ways. The tools disagree by a factor of three, and dollars are not what binds.

A September 2026 claude-mem 13.24.1 case study: moving observations from Sonnet 5 to Qwen2.5-Coder-7B, with measured timeout and output-quality limits.

An inspected agent configuration shared by Claude Code and Codex: immutable releases, 4 execution layers, BM25 skill routing and the gaps found. Full report to read online.

What Back Market measured after 2 months on OpenRouter: a per-person budget, a provider shortlist, a longer liability chain. Full report to read online.

Claude Code selected flow-lean but skipped its footer. A casing fix showed why installation, selection, and behavior need separate evidence.

Flow Lean fused three response skills. Its historical eval beat each comparator and caught a candidate offering a migration against an inferred target.

I ran claude-mem for four and a half months. Six things were broken, four of them since March, and none ever raised an error.

Share Claude Code and Codex instructions, skills and MCP definitions through versioned releases, host adapters and checks of installed and runtime behavior.

Two conference accounts describe CLAUDE.md bloat. How to scope project facts, procedures and response preferences, then verify loading and behavior.

Choose context controls from L0 to L5 according to the failure you observe, from project documentation to scoped rules, behavior checks and shared configuration.

Compare eager and deferred MCP tool loading, distinguish context use from billed tokens, and choose servers for a concrete workflow need.

An illustrative 243-file migration split across bounded agents, with a shared brief, local checks and sequential merge validation.

Hooks are shell scripts with your user permissions. MCP servers are third-party code with access to your credentials. Their timing and access depend on the configured events and server.

Three configuration layers for project context, daily tools and persistent memory, with checks for what loads and how it behaves.

Separate test creation from implementation, verify the expected failure, and give automated TDD retries an explicit exit path.

Portable instructions require neutral sources, generated runtime outputs, release controls, and behavioral tests. Native primitives alone do not provide portability.

A map of context engineering responsibilities: architecture, specifications, agent identity and evaluation, with practical directions for existing skills.

Compare RTK, Tokenade, Headroom and prompt caching by mechanism, integration and evidence. Smaller tool output does not establish a cheaper completed task.

Use L0 to L5 to diagnose context drift, then maintain adherence through observation, repair, and replay instead of treating setup as finished.

Anthropic measured merged PRs; METR measured task duration in a different setting. What these results and long-context research establish, and what remains a hypothesis.

6 human commit authors plus Claude in our git history (May 2026 snapshot). What the commit patterns actually look like after months of Claude Code, beyond the marketing claims.

The concepts I wish I’d known before week one: the agent loop, instruction scopes, context management, skill invocation, hooks, and client permission checks.

Choose between Claude Code and Cowork, then follow the Start, Build, or Scale path that matches your role and current operating problem.

Nine months of AI configuration in one production project: evolving responsibilities, profile-based generation and a measured reduction in always-on lines.

Everyone talks about shipping 10x faster with AI. Nobody talks about accumulating debt 10x faster. 7 months of production data from a real EdTech platform.

A non-developer modified 80 files in production in 10 days with Cursor AI. Exact timeline, AI config setup, and what it means for engineering teams in 2026.

Jeremy Twei coined it. Addy Osmani popularized it. Margaret-Anne Storey extended it to teams. Here's what I built to fight all three.